| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12061467091910699, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009278051609162076, | |
| "grad_norm": 0.16432242095470428, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3715, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009278051609162076, | |
| "eval_loss": 10.37634563446045, | |
| "eval_runtime": 1.9843, | |
| "eval_samples_per_second": 366.368, | |
| "eval_steps_per_second": 91.718, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01855610321832415, | |
| "grad_norm": 0.17450982332229614, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3866, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02783415482748623, | |
| "grad_norm": 0.20075102150440216, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3751, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0371122064366483, | |
| "grad_norm": 0.20002366602420807, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3753, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04639025804581038, | |
| "grad_norm": 0.16843415796756744, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3802, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05566830965497246, | |
| "grad_norm": 0.18495182693004608, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3753, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06494636126413453, | |
| "grad_norm": 0.1839418262243271, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3711, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0742244128732966, | |
| "grad_norm": 0.19310903549194336, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3778, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08350246448245868, | |
| "grad_norm": 0.18260075151920319, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3754, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09278051609162076, | |
| "grad_norm": 0.2032376527786255, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3641, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10205856770078284, | |
| "grad_norm": 0.19692528247833252, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3718, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11133661930994491, | |
| "grad_norm": 0.1963738352060318, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3822, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12061467091910699, | |
| "grad_norm": 0.21577142179012299, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3725, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12061467091910699, | |
| "eval_loss": 10.370198249816895, | |
| "eval_runtime": 1.9865, | |
| "eval_samples_per_second": 365.979, | |
| "eval_steps_per_second": 91.621, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 21757817782272.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |